Digital Twin-Based Analysis and Optimization for Design and Planning of Production Lines

Lee, Donggun; Kim, Chong-Keun; Yang, Jinho; Cho, Kang-Yeon; Choi, Jong-Hwan; Noh, Sang Do; Nam, Seunghoon

doi:10.3390/machines10121147

Cited by 10 publications

(3 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several benefits can be derived from the adoption of the DT concept in organizations, and, in particular, the manufacturing sector [5], which provides advantages in an environment in which industrial players are forced to react more quickly, reduce their costs, show great flexibility [6], and be able to predict changes in their business. The aerospace and defense sectors are examples of sectors where the digital twin concept is deployed more.…”

Section: Introduction 1background and Motivationmentioning

confidence: 99%

A Deep-Reinforcement-Learning-Based Digital Twin for Manufacturing Process Optimization

Khdoudi,

Masrour,

El Hassani

et al. 2024

Systems

View full text Add to dashboard Cite

In the context of Industry 4.0 and smart manufacturing, production factories are increasingly focusing on process optimization, high product customization, quality improvement, cost reduction, and energy saving by implementing a new type of digital solutions that are mainly driven by Internet of Things (IoT), artificial intelligence, big data, and cloud computing. By the adoption of the cyber–physical systems (CPSs) concept, today’s factories are gaining in synergy between the physical and the cyber worlds. As a fast-spreading concept, a digital twin is considered today as a robust solution for decision-making support and optimization. Alongside these benefits, sectors are still working to adopt this technology because of the complexity of modeling manufacturing operations as digital twins. In addition, attempting to use a digital twin for fully automatic decision-making adds yet another layer of complexity. This paper presents our framework for the implementation of a full-duplex (data and decisions) specific-purpose digital twin system for autonomous process control, with plastic injection molding as a practical use-case. Our approach is based on a combination of supervised learning and deep reinforcement learning models that allows for an automated updating of the virtual representation of the system, in addition to an intelligent decision-making process for operational metrics optimization. The suggested method allows for improvements in the product quality while lowering costs. The outcomes demonstrate how the suggested structure can produce high-quality output with the least amount of human involvement. This study shows how the digital twin technology can improve the productivity and effectiveness of production processes and advances the use of the technology in the industrial sector.

show abstract

Section: Introduction 1background and Motivationmentioning

confidence: 99%

A Deep-Reinforcement-Learning-Based Digital Twin for Manufacturing Process Optimization

Khdoudi,

Masrour,

El Hassani

et al. 2024

Systems

View full text Add to dashboard Cite

show abstract

“…One of the most advanced IT systems designed to solve these difficulties is the concept of a digital twin [3,4]. Research and work on its implementation are carried out in many fields, including robotics and manufacturing [5,6], energy [7], mining [8,9], agriculture [10], logistics, specifically road [11], rail [12], watercraft [13], and aircraft transportation [14,15], or in medicine [16]. The intensive development of this technology also applies to the construction industry, including civil and bridge engineering [17][18][19].…”

Section: Introductionmentioning

confidence: 99%

The Concept of Creating Digital Twins of Bridges Using Load Tests

Jasiński,

Łaziński,

Piotrowski

2023

Sensors

View full text Add to dashboard Cite

The paper sheds light on the process of creating and validating the digital twin of bridges, emphasizing the crucial role of load testing, BIM models, and FEM models. At first, the paper presents a comprehensive definition of the digital twin concept, outlining its core principles and features. Then, the framework for implementing the digital twin concept in bridge facilities is discussed, highlighting its potential applications and benefits. One of the crucial components highlighted is the role of load testing in the validation and updating of the FEM model for further use in the digital twin framework. Load testing is emphasized as a key step in ensuring the accuracy and reliability of the digital twin, as it allows the validation and refinement of its models. To illustrate the practical application and issues during tuning and validating the FEM model, the paper provides an example of a real bridge. It shows how a BIM model is utilized to generate a computational FEM model. The results of the load tests carried out on the bridge are discussed, demonstrating the importance of the data obtained from these tests in calibrating the FEM model, which forms a critical part of the digital twin framework.

show abstract

“…Ricondo et al [37] study a digital twin model for the simulation optimization of manufacturing systems. Additionally, Lee et al [38] design a digital twin and develop a simulation model to optimize the processes and production lines of a dynamic production environment.…”

Section: Introductionmentioning

confidence: 99%

The Evaluation and Improvement of the Production Processes of an Automotive Industry Company via Simulation and Optimization

Utku

2023

Sustainability

View full text Add to dashboard Cite

Production delays are significant problems for the loss of goodwill of the customers and the loss of profits associated with them. The delays may accrue as a result of insufficient resource planning and poorly designed unsatisfactory procedures. In this study, a new mathematical model is proposed to optimize the production processes by minimizing production delays, and a simulation model is developed to test the alternative facility designs. The purpose is to increase customer satisfaction by ensuring that the products are delivered timely and preventing lost sales in an automotive company that manufactures garbage collectors by using real data. The mixed-integer programming problem related to the minimization of production delays is solved by the GAMS CPLEX 24.1.3 software. In this way, the total delay in the production area is minimized by the mathematical model to prevent labor and time loss. Accordingly, the alternative designs are investigated for the improvement of the production processes by using discrete system simulation. A system analysis is performed to determine the bottlenecks in the production processes by developing a simulation model via the ARENA simulation software. With the proposed facility layout alternatives, the delays are eliminated, the total production time is reduced, and an increase in production efficiency is observed.

show abstract

Digital Twin-Based Analysis and Optimization for Design and Planning of Production Lines

Cited by 10 publications

References 39 publications

A Deep-Reinforcement-Learning-Based Digital Twin for Manufacturing Process Optimization

A Deep-Reinforcement-Learning-Based Digital Twin for Manufacturing Process Optimization

The Concept of Creating Digital Twins of Bridges Using Load Tests

The Evaluation and Improvement of the Production Processes of an Automotive Industry Company via Simulation and Optimization

Contact Info

Product

Resources

About